{"id":"https://openalex.org/W2407733515","doi":"https://doi.org/10.21437/interspeech.2011-167","title":"Exploiting phone-class specific landmarks for refinement of segment boundaries in TTS databases","display_name":"Exploiting phone-class specific landmarks for refinement of segment boundaries in TTS databases","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2407733515","doi":"https://doi.org/10.21437/interspeech.2011-167","mag":"2407733515"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-167","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081105332","display_name":"Vijayaditya Peddinti","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vijayaditya Peddinti","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113522207","display_name":"Kishore Prahallad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kishore Prahallad","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081105332"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8552,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81909335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"429","last_page":"432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8340265154838562},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6316275596618652},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.62947678565979},{"id":"https://openalex.org/keywords/classification-of-discontinuities","display_name":"Classification of discontinuities","score":0.6110662817955017},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6098343729972839},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5430963635444641},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5358741283416748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5261546969413757},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4893597960472107},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4341583549976349},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4249180853366852},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42388254404067993},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4102259576320648},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.4100120961666107},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33953434228897095},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08187258243560791}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8340265154838562},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6316275596618652},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.62947678565979},{"id":"https://openalex.org/C15627037","wikidata":"https://www.wikidata.org/wiki/Q541961","display_name":"Classification of discontinuities","level":2,"score":0.6110662817955017},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6098343729972839},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5430963635444641},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5358741283416748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5261546969413757},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4893597960472107},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4341583549976349},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4249180853366852},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42388254404067993},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4102259576320648},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.4100120961666107},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33953434228897095},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08187258243560791},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-167","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W28591292","https://openalex.org/W156918189","https://openalex.org/W943204654","https://openalex.org/W1494496989","https://openalex.org/W1594082249","https://openalex.org/W1655397831","https://openalex.org/W1967177300","https://openalex.org/W2045157414","https://openalex.org/W2077529289","https://openalex.org/W2103904886","https://openalex.org/W2104653033","https://openalex.org/W2119315826","https://openalex.org/W2398444131"],"related_works":["https://openalex.org/W1972096828","https://openalex.org/W2529137940","https://openalex.org/W4302048708","https://openalex.org/W2359913921","https://openalex.org/W1595194509","https://openalex.org/W4239740410","https://openalex.org/W1996195943","https://openalex.org/W4205298958","https://openalex.org/W1974738623","https://openalex.org/W2153098279"],"abstract_inverted_index":{"High":[0],"accuracy":[1,90,110],"speech":[2,18],"segmentation":[3],"methods":[4],"invariably":[5],"depend":[6],"on":[7],"manually":[8,118],"labelled":[9,119],"data.":[10,120],"However":[11],"under-resourced":[12],"languages":[13],"do":[14],"not":[15],"have":[16],"annotated":[17],"corpora":[19],"required":[20],"for":[21],"training":[22,106],"these":[23],"segmentors.":[24],"In":[25],"this":[26,56],"paper":[27],"we":[28],"propose":[29],"a":[30],"boundary":[31],"refinement":[32,51,84],"technique":[33,85,101,107],"which":[34],"uses":[35],"knowledge":[36,57],"of":[37,45,55,61,78,91,95,116],"phone-class":[38],"specific":[39],"subband":[40],"energy":[41],"events,":[42],"in":[43,63,69,75],"place":[44],"manual":[46],"labels,":[47],"to":[48,111],"guide":[49],"the":[50,76,99,109,114],"process.":[52],"The":[53,82],"use":[54,115],"enables":[58],"proper":[59],"placement":[60],"boundaries":[62,87],"regions":[64],"with":[65,88,102],"multiple":[66],"spectral":[67],"discontinuities":[68],"close":[70],"proximity.":[71],"It":[72],"also":[73],"helps":[74],"correction":[77],"large":[79],"alignment":[80],"errors.":[81],"proposed":[83,100],"provides":[86],"an":[89],"82%":[92],"within":[93],"20ms":[94],"actual":[96],"boundary.":[97],"Combining":[98],"iterative":[103],"isolated":[104],"HMM":[105],"boosts":[108],"89%,":[112],"without":[113],"any":[117]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
